Non-destructive Quality Analysis of Kamod Oryza Sativa SSP Indica (Indian Rice) Using Machine Learning Technique

Abstract

Rice is one of the most important cereal grains. The paper presents a solution for quality evaluation and grading of Krishna Kamod rice using image processing and soft computing technique. In this paper basic problem of rice industry for quality assessment is defined which is traditionally done manually by human inspector. Machine vision provides one alternative for an automated, non-destructive and cost-effective technique. The proposed method for quality assessment of INDIAN KAMOD ORYZA SATIVA SSP INDICA (Krishna Kamod Rice) using image processing and multi-layer feed forward neural network technique which achieves high degree of quality than human vision inspection. The proposed algorithm based on morphological features is developed for counting the number of Krishna Kamod rice seeds with long seeds as well as small seeds. A trained multi-layer feed forward neural network based classifier is developed for identification of unknown rice seed quality.